Effortless customer engagement is top of mind for Quinn Banks, senior product marketing manager at Farmers Insurance -- and he's spearheading the implementation of machine learning to get the company there. "We are working with machine learning to make our app more efficient when customers come in, or even to anticipate what a customer will need when they come into the application, based on their habits, their environmental changes, even Read More ... Tags: Corporate Enterprises Computer systems Customers Artificial intelligence Machine intelligence Machine learning Google crams machine learning into smartwatches in A.I. push Google is bringing artificial intelligence to a whole new set of devices, including Android Wear 2.0 smartwatches and the Raspberry Pi board, later this year. These devices don't require a set of powerful CPUs and GPUs to carry out machine-learning tasks. Google researchers are instead trying to lighten the hardware load to carry out basic A.I. tasks, as exhibited by last week's release of the Android Wear 2.0 operating system Read More ... Tags: Smart Devices Computer systems Smart Watches Artificial intelligence Machine intelligence Machine learning Wearable devices In this video from the 2017 HPC Advisory Council Stanford Conference, DK Panda presents: Best Practices: Designing HPC & Deep Learning Middleware for Exascale Systems. "This talk will focus on challenges in designing runtime environments for exascale systems with millions of processors and accelerators to support various programming models.

Chichewa (also Chewa and Nyanja) is a Bantu language of about 12 Million speakers, spoken mostly in Malawi and around. Lines 216-221 have the code commented out that enable it to be run from command line instead of via a web form. The parser implements the description of Chichewa affixes outline in: Mchombo, Sam, (2004). Cambridge Syntax Guides Page references in the comments of the code are references to pages in this text. The parser was used as part of my PhD, so you can use this citation if you want to reference the code in a publication: Munro, Robert (2012). It was built to compare a hand-crafted parser with morphological parsers that learned using superivsed and unsupervised machine learning.

In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source sentence can help to determine the correct word order of the translated words. In this paper, we present a novel reordering approach utilizing a neural network and dependency-based embeddings to predict whether the translations of two source words linked by a dependency relation should remain in the same order or should be swapped in the translated sentence. Experiments on Chinese-to-English translation show that our approach yields a statistically significant improvement of 0.57 BLEU point on benchmark NIST test sets, compared to our prior state-of-the-art statistical MT system that uses sparse dependency-based reordering features.

Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents. Text classification just makes up for these deficiencies. In this paper, we propose a novel summarization system called TCSum, which leverages plentiful text classification data to improve the performance of multi-document summarization. TCSum projects documents onto distributed representations which act as a bridge between text classification and summarization. It also utilizes the classification results to produce summaries of different styles. Extensive experiments on DUC generic multi-document summarization datasets show that, TCSum can achieve the state-of-the-art performance without using any hand-crafted features and has the capability to catch the variations of summary styles with respect to different text categories.

Matrix factorization is a core technique in many machine learning problems, yet also presents a nonconvex and often difficult-to-optimize problem. In this paper we present an approach based upon polynomial optimization techniques that both improves the convergence time of matrix factorization algorithms and helps them escape from local optima. Our method is based on the realization that given a joint search direction in a matrix factorization task, we can solve the ``subspace search'' problem (the task of jointly finding the steps to take in each direction) by solving a bivariate quartic polynomial optimization problem. We derive two methods for solving this problem based upon sum of squares moment relaxations and the Durand-Kerner method, then apply these techniques on matrix factorization to derive a direct coordinate descent approach and a method for speeding up existing approaches. On three benchmark datasets we show the method substantially improves convergence speed over state-of-the-art approaches, while also attaining lower objective value.

Trivia is any fact about an entity which is interesting due to its unusualness, uniqueness or unexpectedness. Trivia could be successfully employed to promote user engagement in various product experiences featuring the given entity. A Knowledge Graph (KG) is a semantic network which encodes various facts about entities and their relationships. In this paper, we propose a novel approach called DBpedia Trivia Miner (DTM) to automatically mine trivia for entities of a given domain in KGs. The essence of DTM lies in learning an Interestingness Model (IM), for a given domain, from human annotated training data provided in the form of interesting facts from the KG. The IM thus learnt is applied to extract trivia for other entities of the same domain in the KG. We propose two different approaches for learning the IM - a) A Convolutional Neural Network (CNN) based approach and b) Fusion Based CNN (F-CNN) approach which combines both hand-crafted and CNN features. Experiments across two different domains - Bollywood Actors and Music Artists reveal that CNN automatically learns features which are relevant to the task and shows competitive performance relative to hand-crafted feature based baselines whereas F-CNN significantly improves the performance over the baseline approaches which use hand-crafted features alone. Overall, DTM achieves an F1 score of 0.81 and 0.65 in Bollywood Actors and Music Artists domains respectively.

Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has gained widespread attention in recent years. Despite the vast amount of research into MCTS, the effect of modifications on the algorithm, as well as the manner in which it performs in various domains, is still not yet fully known. In particular, the effect of using knowledge-heavy rollouts in MCTS still remains poorly understood, with surprising results demonstrating that better-informed rollouts often result in worse-performing agents. We present experimental evidence suggesting that, under certain smoothness conditions, uniformly random simulation policies preserve the ordering over action preferences. This explains the success of MCTS despite its common use of these rollouts to evaluate states. We further analyse non-uniformly random rollout policies and describe conditions under which they offer improved performance.

Estimating the joint probability density function of a dataset is a central task in many machine learning applications. In this work we address the fundamental problem of kernel bandwidth estimation for variable kernel density estimation in high-dimensional feature spaces. We derive a variable kernel bandwidth estimator by minimizing the leave-one-out entropy objective function and show that this estimator is capable of performing estimation in high-dimensional feature spaces with great success. We compare the performance of this estimator to state-of-the art maximum-likelihood estimators on a number of representative high-dimensional machine learning tasks and show that the newly introduced minimum leave-one-out entropy estimator performs optimally on a number of high-dimensional datasets considered.

Inference from an observed or hypothesized condition to a plausible cause or explanation for this condition is known as abduction. For many tasks, the acquisition of the necessary knowledge by machine learning has been widely found to be highly effective. However, the semantics of learned knowledge are weaker than the usual classical semantics, and this necessitates new formulations of many tasks. We focus on a recently introduced formulation of the abductive inference task that is thus adapted to the semantics of machine learning. A key problem is that we cannot expect that our causes or explanations will be perfect, and they must tolerate some error due to the world being more complicated than our formalization allows. This is a version of the qualification problem, and in machine learning, this is known as agnostic learning. In the work by Juba that introduced the task of learning to make abductive inferences, an algorithm is given for producing k-DNF explanations that tolerates such exceptions: if the best possible k-DNF explanation fails to justify the condition with probability ε, then the algorithm is promised to find a k-DNF explanation that fails to justify the condition with probability at most O(nkε), where n is the number of propositional attributes used to describe the domain. Here, we present an improved algorithm for this task. When the best k- DNF fails with probability ε, our algorithm finds a k-DNF that fails with probability at most O ̃(nk/2ε) (i.e., suppressing logarithmic factors in n and 1/ε). We also examine the empirical advantage of this new algorithm over the previous algorithm in two test domains, one of explaining conditions generated by a “noisy” k-DNF rule, and another of explaining conditions that are actually generated by a linear threshold rule.

From Google's self-driving cars to Amazon's purchase predictions, artificial intelligence (AI) is any program that does something we would normally consider an intelligent human act. But as AI technology continues to develop rapidly, prominent personalities including Stephen Hawking and Bill Gates have voiced their concern about the rise of super-intelligent machines. They question they ask is: "How dangerous could AI become?" We've all watched at least one science fiction movie where an intelligent robot goes rogue and tries to destroy all humanity. And while we certainly aren't ignoring the valid concerns raised about super-intelligent machines, it is possible that AI and humans can be complementary.